Evaluating the Effectiveness of Chain-of-Thought Prompting: Insights from a Quantitative Meta-Analysis and Experiments Across Models and Datasets
Chain-of-thought prompting primarily helps on tasks involving mathematical, logical, or algorithmic reasoning, with limited benefits on other types of reasoning tasks.
LifeGPT: A Topology-Agnostic Transformer Model for Accurately Simulating Conway's Game of Life
A decoder-only transformer model, LifeGPT, can accurately simulate the dynamics of Conway's Game of Life on a toroidal grid without any prior knowledge of the grid size or boundary conditions.
Enhancing Transformer Models with Möbius Attention for Improved Linguistic Pattern Capture
Möbius Attention, a novel attention mechanism based on Möbius transformations, enhances the expressivity of Transformer models by enabling them to capture more intricate linguistic patterns and relationships between tokens.
Local-Global Representation Alignment for Robust Time Series Classification
The proposed LogoRA framework employs a two-branch encoder to extract both local and global representations from time series data, and utilizes various alignment strategies to learn domain-invariant features for robust time series classification across different domains.
Efficient Compression and Compressive Search of Large Datasets Using Hierarchical Clustering
panCAKES, a novel hierarchical compression algorithm, enables efficient, exact k-NN and ρ-NN search on compressed data by leveraging the low-dimensional structure of the data.
제약된 일반 합 게임을 위한 빠른 Newton 솔버 - 잔류 하강 미분 동적 게임(RD3G)
제안된 RD3G 알고리즘은 에이전트들이 보상과 상태 제약을 통해 결합된 문제에 대한 국소 내쉬 균형을 찾는다.
Residual Descent Differential Dynamic Game (RD3G): A Fast Newton-Based Solver for Constrained Multi-Agent Game-Control Problems
The proposed RD3G algorithm is a novel Newton-based method that efficiently solves constrained multi-agent game-control problems by partitioning the inequality constraints and removing dual variables associated with inactive constraints to reduce the scale of the linear problem in each iteration.
高效計算 Lempel-Ziv (LZ77) 分解的子線性時間算法
我們提出了第一個在亞線性時間內計算 LZ77 分解的算法,打破了近50年來一直存在的線性時間障礙。
Improving Large Language Model Reasoning Through Adaptive Coarse-to-Fine Refinement
MAGICORE, a framework for Multi Agent Iteration for Coarse-to-fine Refinement, improves Large Language Model reasoning by adaptively applying coarse-grained aggregation or fine-grained, iterative multi-agent refinement based on problem difficulty.
선형 시간 이하의 Lempel-Ziv (LZ77) 요인화
본 논문은 Lempel-Ziv (LZ77) 요인화를 선형 시간 이하로 계산할 수 있는 최초의 알고리즘을 제시한다.
© 2024 by Linnk AI